A multi-modal YOLOv5 model fuses GPT text descriptions via cross-attention and convolutional fusion to achieve better UI control detection than baseline on 16,000+ screenshots.
Promptcap: Prompt-guided image captioning for vqa with gpt-3
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-modal user interface control detection using cross-attention
A multi-modal YOLOv5 model fuses GPT text descriptions via cross-attention and convolutional fusion to achieve better UI control detection than baseline on 16,000+ screenshots.